The Awomo-PhysicalRSI team has developed Awomo-SimDataEngine, a system that enhances robot training data generation. It combines asset and scene generation with robot demonstration synthesis, leading to improved training success rates.
A new approach to multi-robot informative path planning utilizes a grid-based GP-Kalman filtering framework. This method improves target monitoring by addressing spatial uncertainty and communication challenges, showing promising results in simulations and real-world tests.
A new edge-based solution called Conductor enhances the planning algorithms of Connected Autonomous Vehicles by creating a unified world model. This method improves trajectory predictions while adhering to strict time constraints, demonstrating superior performance in simulations.
ProAct is a new framework that enhances the predictability of action generation in robotics. It improves performance in simulation and real-world tasks while optimizing efficiency.